bmad-tea-evaluate
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes Python scripts located within the project's
_bmad/scripts/directory (resolve_customization.pyandresolve_config.py) to handle customization and configuration management. This execution occurs automatically during the skill's activation sequence. - [COMMAND_EXECUTION]: The skill uses shell commands to interact with various evaluation and package management tools, including
npm,tea-evaluate, andeval-quality. These are used for installing dependencies, checking evaluation manifests, and running the evaluation pipeline. - [DYNAMIC_EXECUTION]: The skill manages and executes JavaScript-based evaluator scripts provided in its
assets/directory (e.g.,agentevals-trajectory.mjs,promptfoo-assertions.mjs). These scripts are copied into the user's evaluation folder and executed to process agent observations and generate scores.
Audit Metadata